© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13094
    Prev
    Next
    INDEX
    Explanations

    words/abbreviations relating to medical procedures and organizations

    oai_token-act-pair · gemini-2.0-flash

    Medical terminology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.93
     مرئيه
    -0.89
    tagHelperRunner
    -0.82
    oredCriteria
    -0.82
    uxxxx
    -0.81
    GOTREF
    -0.80
     mergeFrom
    -0.79
     '\\;'
    -0.78
    reactstrap
    -0.78
     Мексичка
    -0.78
    POSITIVE LOGITS
    関連項目
    0.48
     flat
    0.44
    flat
    0.42
    setIcon
    0.42
    std
    0.42
    かせ
    0.41
     lijn
    0.39
    ola
    0.38
     succeeding
    0.38
    сс
    0.38
    Activations Density 4.197%

    No Known Activations